# coding=utf8
import re
regex = r"(?<=<a>)(\s*?<b>([^<]+)<\/b>)(\s*?<b>([^<]+)<\/b>)?(\s*?<b>([^<]+)<\/b>)?(\s*?<b>([^<]+)<\/b>)?"
test_str = '''
<a>
<b>test11</b>
</a>
<a>
<b>test21</b>
<b>test22</b>
</a>
<a>
<b>test31</b>
<b>test32</b>
<b>test33</b>
</a>
<a>
<b>test41</b>
<b>test42</b>
<b>test43</b>
<b>test44</b>
</a>
<c>
<b>test51</b>
<b>test52</b>
</c>
'''
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
if (groupNum % 2 == 0) & (match.group(groupNum) != None):
print (match.group(groupNum) )
